基于人工智能的音频事件分类系统研究  

Research on Audio Event Classification System Based on Artificial Intelligence

作　　者：付兆婷 FU Zhaoting(Baiyin College,Baiyin Open University,Baiyin 730900,China)

机构地区：[1]白银开放大学白银学院,甘肃白银730900

出　　处：《电声技术》2024年第3期45-47,共3页Audio Engineering

摘　　要：针对音频时间分类领域中的挑战,提出一种基于人工智能的音频分类系统,并结合传统隐马尔可夫模型(Hidden Markov Model,HMM)优化方法,采用UrbanSound数据集进行测试。首先,介绍了音频分类系统的框架。其次,针对传统HMM模型的不足,提出一种基于模型融合的HMM优化方法,通过多模型投票的方式提高分类的准确性和健壮性。最后,在MATLAB平台上进行实验。实验结果表明,该方法的准确率、精确率、召回率均优于传统HMM模型。The article proposes an artificial intelligence based audio classification system to address the challenges in the field of audio time classification,combined with traditional Hidden Markov Model(HMM)optimization methods,and tested using the UrbanSound dataset.Firstly,the framework of the audio classification system was introduced.Secondly,in response to the shortcomings of traditional HMM models,a model fusion based HMM optimization method is proposed to improve the accuracy and robustness of classification through multiple model voting.Finally,conduct experiments on the MATLAB platform.The experimental results show that the accuracy,precision,and recall of this method are superior to traditional HMM models.

关 键 词：人工智能 音频分类 模型融合 

分 类 号：TN912.34[电子电信—通信与信息系统]